Temporal feature selection for time-series prediction

We present a feature selection method for multivariate time-series prediction. It aims to use the best sliding window size and delay for each explanatory variable, which are usually fixed. The idea is to convert the original time-series into a set of cumulative sum with different length. The combina...

Full description

Saved in:
Bibliographic Details
Main Authors: Hido, S., Morimura, T.
Format: Conference Proceeding
Language:English
Subjects:
Computational modeling
Delay
Hidden Markov models
Input variables
Pattern recognition
Prediction algorithms
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 3560
container_issue
container_start_page 3557
container_title
container_volume
creator Hido, S.
Morimura, T.
description We present a feature selection method for multivariate time-series prediction. It aims to use the best sliding window size and delay for each explanatory variable, which are usually fixed. The idea is to convert the original time-series into a set of cumulative sum with different length. The combinations of cumulative sum variables obtaining nonzero weights in sparse learning algorithms represent the optimal temporal effects from explanatory variables to the target variable. Experiments show that the method performs better than conventional methods in regression problems.
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_6460933</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6460933</ieee_id><sourcerecordid>6460933</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-2fa6fc9c39c52bc228a74b83a56d7b3377a51c9a27d8c12b271bfb4af0ed991a3</originalsourceid><addsrcrecordid>eNotzMtKAzEUgOFoFRxrn8DNvEAg5-S-lOINCm7quiSZE0iZcYZkXPj2QnX1Lz74r9jOW6e8F0YpEP6adegkcKus3lwMlLESEYy6YR0IDVwZDXfsvrWzECikdh3TR5qWuYaxzxTW70p9o5HSWuavPs-1X8tEvFEt1Pql0lAu9MBucxgb7f67ZZ8vz8f9Gz98vL7vnw68gNUrxxxMTj5JnzTGhOiCVdHJoM1go5TWBg3JB7SDS4ARLcQcVciCBu8hyC17_PsWIjottUyh_pyMMsJLKX8B55FFnw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Temporal feature selection for time-series prediction</title><source>IEEE Xplore All Conference Series</source><creator>Hido, S. ; Morimura, T.</creator><creatorcontrib>Hido, S. ; Morimura, T.</creatorcontrib><description>We present a feature selection method for multivariate time-series prediction. It aims to use the best sliding window size and delay for each explanatory variable, which are usually fixed. The idea is to convert the original time-series into a set of cumulative sum with different length. The combinations of cumulative sum variables obtaining nonzero weights in sparse learning algorithms represent the optimal temporal effects from explanatory variables to the target variable. Experiments show that the method performs better than conventional methods in regression problems.</description><identifier>ISSN: 1051-4651</identifier><identifier>ISBN: 9781467322164</identifier><identifier>ISBN: 1467322164</identifier><identifier>EISSN: 2831-7475</identifier><identifier>EISBN: 9784990644109</identifier><identifier>EISBN: 4990644107</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational modeling ; Delay ; Hidden Markov models ; Input variables ; Pattern recognition ; Prediction algorithms ; Training</subject><ispartof>Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), 2012, p.3557-3560</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6460933$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2056,54553,54918,54930</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6460933$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Hido, S.</creatorcontrib><creatorcontrib>Morimura, T.</creatorcontrib><title>Temporal feature selection for time-series prediction</title><title>Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)</title><addtitle>ICPR</addtitle><description>We present a feature selection method for multivariate time-series prediction. It aims to use the best sliding window size and delay for each explanatory variable, which are usually fixed. The idea is to convert the original time-series into a set of cumulative sum with different length. The combinations of cumulative sum variables obtaining nonzero weights in sparse learning algorithms represent the optimal temporal effects from explanatory variables to the target variable. Experiments show that the method performs better than conventional methods in regression problems.</description><subject>Computational modeling</subject><subject>Delay</subject><subject>Hidden Markov models</subject><subject>Input variables</subject><subject>Pattern recognition</subject><subject>Prediction algorithms</subject><subject>Training</subject><issn>1051-4651</issn><issn>2831-7475</issn><isbn>9781467322164</isbn><isbn>1467322164</isbn><isbn>9784990644109</isbn><isbn>4990644107</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotzMtKAzEUgOFoFRxrn8DNvEAg5-S-lOINCm7quiSZE0iZcYZkXPj2QnX1Lz74r9jOW6e8F0YpEP6adegkcKus3lwMlLESEYy6YR0IDVwZDXfsvrWzECikdh3TR5qWuYaxzxTW70p9o5HSWuavPs-1X8tEvFEt1Pql0lAu9MBucxgb7f67ZZ8vz8f9Gz98vL7vnw68gNUrxxxMTj5JnzTGhOiCVdHJoM1go5TWBg3JB7SDS4ARLcQcVciCBu8hyC17_PsWIjottUyh_pyMMsJLKX8B55FFnw</recordid><startdate>201211</startdate><enddate>201211</enddate><creator>Hido, S.</creator><creator>Morimura, T.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201211</creationdate><title>Temporal feature selection for time-series prediction</title><author>Hido, S. ; Morimura, T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-2fa6fc9c39c52bc228a74b83a56d7b3377a51c9a27d8c12b271bfb4af0ed991a3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Computational modeling</topic><topic>Delay</topic><topic>Hidden Markov models</topic><topic>Input variables</topic><topic>Pattern recognition</topic><topic>Prediction algorithms</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Hido, S.</creatorcontrib><creatorcontrib>Morimura, T.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hido, S.</au><au>Morimura, T.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Temporal feature selection for time-series prediction</atitle><btitle>Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)</btitle><stitle>ICPR</stitle><date>2012-11</date><risdate>2012</risdate><spage>3557</spage><epage>3560</epage><pages>3557-3560</pages><issn>1051-4651</issn><eissn>2831-7475</eissn><isbn>9781467322164</isbn><isbn>1467322164</isbn><eisbn>9784990644109</eisbn><eisbn>4990644107</eisbn><abstract>We present a feature selection method for multivariate time-series prediction. It aims to use the best sliding window size and delay for each explanatory variable, which are usually fixed. The idea is to convert the original time-series into a set of cumulative sum with different length. The combinations of cumulative sum variables obtaining nonzero weights in sparse learning algorithms represent the optimal temporal effects from explanatory variables to the target variable. Experiments show that the method performs better than conventional methods in regression problems.</abstract><pub>IEEE</pub><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1051-4651
ispartof Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), 2012, p.3557-3560
issn 1051-4651
2831-7475
language eng
recordid cdi_ieee_primary_6460933
source IEEE Xplore All Conference Series
subjects Computational modeling
Delay
Hidden Markov models
Input variables
Pattern recognition
Prediction algorithms
Training
title Temporal feature selection for time-series prediction
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T12%3A33%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Temporal%20feature%20selection%20for%20time-series%20prediction&rft.btitle=Proceedings%20of%20the%2021st%20International%20Conference%20on%20Pattern%20Recognition%20(ICPR2012)&rft.au=Hido,%20S.&rft.date=2012-11&rft.spage=3557&rft.epage=3560&rft.pages=3557-3560&rft.issn=1051-4651&rft.eissn=2831-7475&rft.isbn=9781467322164&rft.isbn_list=1467322164&rft_id=info:doi/&rft.eisbn=9784990644109&rft.eisbn_list=4990644107&rft_dat=%3Cieee_CHZPO%3E6460933%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-2fa6fc9c39c52bc228a74b83a56d7b3377a51c9a27d8c12b271bfb4af0ed991a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6460933&rfr_iscdi=true